Key points are not available for this paper at this time.
解决了在雷达理论中出现的以下统计问题。有关随机变量₁, ₙ的联合密度有两个假设 A: PA (x₁, , xₙ) = ₈ = ₁ⁿ {2xᵢ de^ - xᵢ^{{2 / d} } }, \\ B: PB (x₁, , xₙ) = 1n₉ = ₁ⁿ {2xⱼ {d + d}e^ - xd^{{2 {d + d}} } } ₈ ₉ {2xᵢ de^ - xᵢ^{{2 / d} } }, \\ 在此 where d > 0, d > 0. 设 = { d / d} > 0. 记ₙ (F, D)为这样一个数,即没有测试可以将假设 A 和 B区分开,错误概率小于F和D,而当> ₙ (F, D)时,有测试存在。证明对于 n = const, D = const 和 F 0\ ₙ (F, D) = n + {1 / F} { {1 / D}} - 1 + o (1)。推导了包含ₙ (F, D)的稳定分布的渐近公式,其中 F = const, D = const 和n。
R. L. Dobrusin (周三) 研究了这个问题。
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: